Automated detection of deformation mechanisms in re-entrant honeycomb auxetics using machine learning

The intricate geometrical configuration of an auxetic structure enables high energy dissipation capacity at the expense of a highly nonlinear mechanical response. Under external stimuli, complicated deformation mechanisms emerge which dictate the extent of energy dissipation. Recently, the new ‘Plastic Hinge Tracing’ method Dhari et al. (2021) was introduced to detect such deformation mechanisms—especially under inclined loadings. This approach is however subjective and cumbersome since it requires monitoring several plastic regions in consecutive deformed configurations. The present study innovatively extends this method by implementing machine learning (ML) techniques for objective detection of deformation modes in auxetics. To this end, a logistic regression ML model was developed to classify the deformation modes of a re-entrant honeycomb structure. The proposed procedure could successfully detect four out of the six deformation modes (‘X’, distorted ‘X’, ‘V’, and ‘V+Z+V’) using the training datasets generated by the finite element analysis and K-means clustering algorithm to label the images. The success of the proposed automated approach lays the foundation for identifying the deformation mechanisms of other auxetics.

Keywords. k-means clustering, machine learning (ML), logistic regression, deformation modes, auxetics, plastic hinges

Singh G, Dhari RS, Javanbakht Z. Automated detection of deformation mechanisms in re-entrant honeycomb auxetics using machine learning. International Journal of Protective Structures. 2024; doi:10.1177/20414196241281069

Simplified explanation

This study is about detecting how certain materials deform under pressure. Imagine you have a special kind of honeycomb structure that bends and changes shape when you push or pull it. We are interested in how this happens because it helps us design stronger materials for things like buildings or airplane parts.

In this study, we used a computer to analyze and predict how these honeycomb shapes would bend using machine learning, which is a bit like teaching a computer to recognize patterns. The computer was able to figure out different ways the honeycomb bends—kind of like how you might fold paper in different shapes—and group these patterns into categories. This helps us understand how to make the honeycomb stronger or better at absorbing energy when it’s hit by something.

So, in simple terms, we taught a computer to look at a honeycomb and predict how it will bend or change shape under different conditions, helping us make better materials for the future!